Articles & Publications | Towards Data Science | Built Horizons

AI & Architecture

Towards a New Approach

The advent of Artificial Intelligence as a discipline has been permeating countless fields, bringing means and methods to previously unresolved challenges, across industries. The fusion of this new techno-science with Architecture is still in its early days but offers promising results. Our thesis proposes to evidence its potential as it is applied to Architecture. More than a mere opportunity, it is to us, shaping a promising discipline per se. Specifically, we offer to apply AI to floorplans analysis, and generation. Our ultimate goal is two-fold: offer a proper classification methodology of floorplans, able to tackle diversity and quantity, while creating a framework for machine learning-based floorplan generation.

Floorplans are indeed a high-dimensional problem, at the crossroad of quantifiable technics, and more qualitative properties. The study of architectural precedent remains too often a hazardous process, that negates the richness of the number of existing resources while lacking in analytical rigor. We offer here a methodology, inspired by current Data Science methodologies, to qualify plans, both through their style and their organization.

At the heart of this project, lies the necessity of inventing meaningful metrics to qualify and classify floorplans. Through the creation of 6 metrics, we propose a framework that captures architecturally relevant parameters of floorplans.

On one hand, Footprint Shape, Orientation, Thickness & Texture are 3 metrics capturing the essence of a given floorplan’s style. On the other hand, Program, Connectivity and Circulation will capture the essence of a given floorplan organization.

The advent of automated classification is in fact the bedrock of the machine learning practices. Our thesis offers to leverage our database of classified plans to evidence the possibility of such tools applied to floorplan generation. Our methodology follows two main intuitions (1) the creation of floorplans is a non-trivial technical challenge, that encompasses standard optimization technics. (2) The design of space is a sequential process, requiring successive design steps across different scales (urban scale, building scale, unit scale). We attempt to capture these two realities by using nested Generative Adversarial Neural Networks. The use of such models will enable us to capture more complexity across encountered floorplans, while breaking down the complexity of the tackled problems into successive steps. To each step will correspond a given model, trained for this particular task.

Overall, our thesis will evidence the possible back and forth between human and machines, that permeates the architectural discipline today. The machine that was once the extension of our pencil, can today be leveraged to map architectural knowledge, and be trained to assist us creating viable design options.

Artificial Intelligence & Architecture

An Exhibit at the Arsenal Pavilion

Artificial Intelligence (AI) has already made its way into the industry, providing it with the means to meet new challenges. Its use in the field of architecture is still in its infancy, but the expected results already obtained are promising. This technology is much more than a mere opportunity, it is without doubt a decisive step forward, quite capable of transforming the architectural practice. This exhibition explores this engagement and its application to the built environment. Defining AI, explaining what it encompasses, both as techniques and as paradigms, is central to understanding its advent in architecture.

AI first needs to be considered from the perspective of the history of science and that of architecture. Rather than a “disruption”, the technological evolution surrounding and supporting AI is the result of a slow maturation. Indeed, the profession has been undergoing a transformation for quite some time. The progressive adoption of technological solutions has already profoundly changed each stage of its value chain: first by exploiting new construction techniques, then by developing appropriate design software, and now by introducing statistical computing capacities, including, in the forefront, data science and artificial intelligence. Henceforth, rather than a radical orbit change, we want to see a change of trajectory whose acceleration is ultimately in the continuity of a practice that has led architecture to what it is today. Modularity, Computer Aided Design (CAD), Parametricism and Artificial Intelligence (AI) are the four inexorably interwoven stages of a sequence that frames the slow hybridization of our practices such as we live them and can imagine them today.

Bringing together concrete examples and recent results achieved in various fields of research, we showcase for the first time an inventory of AI’s presence in architecture and a panorama of the latest advances in this field. Facade, plan, structure, perspective : as many scales for measuring the city to which AI can already contribute, whether real or hypothetical.

Between current theory and experimentation, this exhibit intends to shed light on the inception of a new technological era, leveraging the architectural practice, while offering it a renewed relevance.

The Advent of Architectural AI

A Historical Perspective

The practice of Architecture, its methods, traditions and know-how are today at the center of passionate debates. Challenged by outsiders, arriving with new practices, and questioned from within, as practitioners doubt of its current state, Architecture is undergoing a truly profound (r)evolution.

Among the factors that will leave a lasting impact on our discipline, technology certainly is one of the main vectors at play. The inception of technological solutions at every step of the value chain has already significantly transformed Architecture. The conception of buildings has in fact already started a slow transformation: first by leveraging new construction technics, then by developing adequate softwares, and eventually today by introducing statistical computing capabilities (including Data Science & AI). Rather than a disruption, we want to see here a continuity that led Architecture through successive evolutions until today. Modularity, Computational Design, Parametricism and finally Artificial Intelligence are to us the four intricated steps of a slow-paced transition. Beyond the historical background, we posit that this evolution is the wireframe of a radical improvement in architectural conception.

KI und Architektur

Der entwerfende Computer

Wie lassen sich Computer, die früher lediglich eine Art erweiterter Zeichenstift waren, heute dazu nutzen, architektonisches Wissen abzubilden? Wie lassen sie sich mit Hilfe maschinellen Lernens trainieren, Architekt*innen bei der Entwurfsarbeit zu unterstützen?

Die hier vorgeschlagene Methode basiert auf einem dreistufigen Prozess: (I) Generierung von Grundrissen, das heißt Optimierung der Erzeugung sehr unterschiedlicher Grundrissentwürfe in großer Zahl, (II) Qualifizierung von Grundrissen, das heißt Entwicklung einer geeigneten Klassifizierungsmethode, und (III) Bereitstellung der Möglichkeit für die Nutzer*innen, die erzeugten Entwürfe zu durchsuchen.

Der Prozess zielt auf eine bessere Differenzier-, Qualifizier- und Modulierbarkeit von Ergebnissen im Vergleich zu bisherigen Programm­anwendungen aus dem Feld der KI-gestützten Raumplanung.

Urban Tech On The Rise

When Machine Learning Disrupts the Real Estate Industry

with Daniel Fink & Pamella Gonçalves

The practice of urban analytic is taking off in the real estate profession. Data science and algorithmic logic are close to the forefront of new urban development practices. “How close?” is the question, but experts consider that digitization will go far beyond intelligent building management systems. New analytical tools with predictive capabilities will dramatically affect the future of urban development, reshaping the real estate industry in the process.


Space Flexibility in The 21st Century

“Flexibility” in architecture refers to the ability of a building to continuously adapt its space layout and even its structure to evolving needs. Stemming from the Modernist movement’s dream which emerged in Japan in the 60’s, the ideal of buildings as constantly evolving entities blends together three main aspirations: the need for a more efficient built environment, an answer to urban centers densification and the humanist promise of a city that would adapt to its citizens.

Buildings are no exception to the rule of supply and demand. They quite naturally go through uneven utilization cycles with ups & downs that can be explained by a broad set of reasons: tenants’ volatility, daily traffic, business seasonality or simply competitive rivalry. But, in contrast to this cyclical nature of use, the real estate industry is stuck with rigidity: the physical rigidity of space and the contractual rigidity of leases. As a result, space is far from being used efficiently. And underperforming spaces are depleting economic value. Given this spatial inefficiency, tuning spaces on a monthly, daily – or even an hourly – basis to achieve greater efficiency seems quite legitimate. At the same time, as city centers increasingly densify, finding available space is a growing concern. Identifying under-utilized spaces and revamping them to match demand is becoming a game-changing paradigm. Finally, as the digital revolution carries the promise of a more personalized user experience, buildings might just be on the verge of following a similar trend. Through constant remodeling and reprogramming, buildings could be tailored to their users’ needs, comfort, and expectations. All in all, building flexible spaces aims to create a more relevant built environment.

However, achieving ‘’architectural flexibility’’ is a challenge that a number of investigations have tried to take up over the past century. From the early stage of the Japanese Metabolist movement to the formal flexibility of contemporary architecture, architects have progressively enshrined the principle of space plasticity. But, by and large, they have rather turned it into a style away from its initial ambition to make functional flexibility an actual operating principle. Today, however, independently of any disciplinarian consideration, the emergence of Big Data powered by algorithmic and semi-automation, may put the promise of architectural flexibility within our reach. There are three good reasons to believe it is no longer just a utopic ideal. First, data and analytics could enable the built environment to better understand and forecast space utilization. Second, semi-automation could help adapt space layouts in near-to-real time, while optimizing users’ comfort and space efficiency. And three, society's fast-moving evolution, including consumers' behavior mutation, could timely leverage the disruptive potential of technologies. On this ground, we propose a revived architectural answer: The Synaptic Building. The Synaptic Building and our manifesto, rooted in the Metabolist tradition, positioning space flexibility as the corner-stone of the 21st-century architectural practice.


From ETH to Harvard - 2011 - 2017

My work is based on a simple conviction: what the hand can spontaneously express, architecture must be able to reflect it. In other words, no architectural concept should escape the simplicity of hand sketching. It is to me a discipline of rigor I apply to my design process, and also a method I use to retrieve the very essence of my projects. Bringing the core concept of each scheme to its most radical form is my constant challenge. In a nutshell:
Few lines, no colors, simplicity and abstraction, to extract the essential.

The portfolio opens with Continuum, a public library for the neighborhood of Back Bay, in Boston. The building had to reconcile a public program of open access stacks, a café, and an amphitheater while ensuring enough privacy for private archives and regulated access. The edifice sits on the river, one foot in the city, one in Back Bay Park. The unicity of the program is achieved through a ring-like scheme composed of three overlapping circles, the outer ring hosting the public program and the most-inner one regrouping the archives. Each circle is made out of a sequence of frames, with varying gaps in between, inducing changing gradients of privacy: wide gaps towards the park, offering a porous façade, allowing for dense light and views for the café and the public stacks; thin openings towards the city, to shelter the private archives and working rooms, while bringing in a filtered light.

Next, is Our Lady of the Fields, a cathedral for South Boston, a project which tries to reconcile faith and ecology, as one singular experience. Following the initial intent of my sketch, the objective was to control views on the exterior, while overlapping religious artworks and natural landscape. As a result, the building, sunk in the ground, offers fourteen curated views on an outside vegetal slope. Each view is in fact framed by two concrete piers, and hosts one of the 14 paintings of the Artist Veronique Charpy, each painting representing one station of the Passion of the Christ. The adapting vegetation in the background, reinforces the sequence: from mineral landscapes for the first stations to a flourishing vegetal scenery for the last stations. The orientation of the Cathedral also ensures that the daily cycle of the sun successively enlights each station, in the proper order, thus reinforcing the symbolic meaning of the sequence.

Steps, is a public thermal bath, located in the Bodio Valley (Switzerland). The building uses a local hot spring source to harvest the heat of the water to power the building. The project offers a sequence of baths, ultimately cooling down the water before releasing it in the river, as required by the ecological policy of Bodio. The alignment of baths, from hot to cool water, progresses under one single linear roof, as the building gradually emerges from the ground. The user is invited to move back and forth along this gradient of pools to fully experience the baths: from warm to cold, from darkness to light, from interior to exterior.

The following project, entitled Refuge, is a hotel located on Stromboli Island (Italy). This volcanic archipelago welcomes an increasing traffic of tourists, hiking around the crater of the volcano. Refuge aims at hosting visitors for the night, while offering a respite to the hikers. The scheme uses a circular shape to curate a 360-degree view on the landscape, while sheltering inside a patio and its pool. The circular ring is composed of a sequence of rooms and bathrooms, interrupted by a lobby, a series of meeting rooms, and an amphitheater overlooking the volcano. As the sun sets, the pool acts as a natural mirror, reflecting the ever-erupting volcano.

Finally, Blocks vs Grid is a proposal for the master plan of South Boston. This project is an attempt to harmonize the need for homogeneity of the urban fabric, with the organic nature of city dwellings. This project plays with the tension between a unifying grid-like “wrapper” around each block, and the heterogeneity of the stacked modular building units. On the street side, the city seems organized and harmonious. Inside each block however, the serendipity of the stacking offers a vibrant environment for the communities, with rich circulations, footbridges, parks and play grounds.